Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

local-env

Supabase seeding, auth user sync, and local development environment setup

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/local-env/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong project-specific reference: highly executable SQL, docker, and script commands with an excellent symptom-to-fix troubleshooting map. Its main weaknesses are duplicated coverage of the GoTrue NULL-token bug across two sections, an inconsistency between the two migration filenames cited as the permanent fix (20260404120000_fix_auth_null_tokens.sql vs 20260404130000_constrain_auth_null_tokens.sql), and verification scripts that are listed but not embedded as explicit workflow checkpoints.

Suggestions

Consolidate the duplicated GoTrue NULL-token coverage (troubleshooting item 6 and the 'Root Cause Summary' section) into a single section, keeping the docker fix command in one place.

Reconcile the conflicting migration filenames: line 153 cites 20260404120000_fix_auth_null_tokens.sql while line 165 cites 20260404130000_constrain_auth_null_tokens.sql as the permanent fix.

Wire validation into the seeding workflow explicitly, e.g. a final step 'Verify: node scripts/verify-auth.mjs' after the SQL inserts, so verification is a checkpoint rather than an optional standalone script.

Dimension	Reasoning	Score
Conciseness	The body is largely lean (dense tables, exact commands, no explanation of concepts Claude already knows), but the GoTrue NULL-token bug is fully covered twice — troubleshooting item 6 with the complete docker command and a dedicated 'Root Cause Summary' table — and the role table carries marginal hex color values. This is more than anchor 4's 'minor instances of over-explanation', fitting anchor 3's 'could be tightened'; anchor 2 is too harsh since there is no concept-explanation padding.	3 / 5
Actionability	Fully executable and copy-paste ready: complete SQL INSERT statements for all three auth tables, exact docker exec/docker restart commands, per-script run commands, and a symptom-to-fix troubleshooting map covering the common cases. Matches the anchor 5 example standard.	5 / 5
Workflow Clarity	Seeding is clearly sequenced (numbered SQL steps plus 'always create all three records together'), and verification tooling exists (verify-auth.mjs, check-auth-schema.mjs health check, 14 regression tests). Not 5 because the verification scripts are not explicitly wired into the workflows as checkpoints (e.g., no 'run verify-auth.mjs after seeding' step); not 3 because sequences and validation tools are clearly present.	4 / 5
Progressive Disclosure	No bundle files exist, so everything is inline by necessity; the single body is well-sectioned with clear headers and easy navigation. The GoTrue deep-dive and full role/color table could arguably live in separate reference files, keeping it below anchor 5's 'well-signaled one-level-deep references'; structure is genuinely good, above anchor 3's 'could be better organized'.	4 / 5
	Total	16 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is domain-specific and distinct, but it reads as a terse noun-phrase list: it states what the skill touches without any action verbs, natural trigger phrases, or a 'Use when' clause. It would benefit from a single sentence in third person that names concrete actions and explicit trigger conditions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when seeding the local Supabase database, creating test users, or fixing local login/auth errors'.

Convert noun phrases into concrete third-person actions, e.g. 'Seeds Supabase test users across auth.users, auth.identities, and user_profiles, and syncs local development environment configuration'.

Include natural trigger terms users would actually say, such as 'Invalid login credentials', 'seed test users', or 'local Supabase setup'.

Dimension	Reasoning	Score
Specificity	"Supabase seeding, auth user sync, and local development environment setup" names the domain and three task areas, but they are noun phrases rather than concrete actions, and coverage has gaps (no mention of login troubleshooting, test users, or migrations that the body covers). Anchor 3 fits; anchor 4 requires several specific actions, and anchor 2's 'actions are minimal or generic' is too harsh for domain-specific task naming.	3 / 5
Completeness	The 'what' is clear (seeding, auth user sync, local dev setup) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. This matches anchor 3 ('clear what but when is missing') exactly, not anchor 4 which requires both.	3 / 5
Trigger Term Quality	Contains relevant keywords ("Supabase", "seeding", "auth user sync", "local development environment") but misses common variations users would naturally say, such as "seed test users", "fix login", "Invalid login credentials", or "database seed". Matches anchor 3 ('some relevant keywords but missing common variations'), below anchor 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	The Supabase-seeding/auth-sync combination is a fairly distinct niche with only minor overlap risk against a hypothetical general Supabase or dev-environment skill. "local development environment setup" is somewhat broad and there are no distinct trigger phrases, keeping it below anchor 5 but above anchor 3's 'could still overlap with similar skills'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	15 / 16 Passed

Repository: zazakia/JetFarm
Path: .agents/skills/local-env/SKILL.md
Revision: bdf360f

Reviewed: 13 hours ago

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

local-env

Table of Contents

Is this your skill?